A competitive strategy for function approximation in Q-learning

Conference Article


International Joint Conference on Artificial Intelligence (IJCAI)





Doc link


Download the digital copy of the doc pdf document


In this work we propose an approach for generalization in continuous domain Reinforcement Learning that, instead of using a single function approximator, tries many different function approximators in parallel, each one defined in a different region of the domain. Associated with each approximator is a relevance function that locally quantifies the quality of its approximation, so that, at each input point, the approximator with highest relevance can be selected. The relevance function is defined using parametric estimations of the variance of the q-values and the density of samples in the input space, which are used to quantify the accuracy and the confidence in the approximation, respectively. These parametric estimations are obtained from a probability density distribution represented as a Gaussian Mixture Model embedded in the input-output space of each approximator. In our experiments, the proposed approach required a lesser number of experiences for learning and produced more stable convergence profiles than when using a single function approximator.


generalisation (artificial intelligence), learning (artificial intelligence).

Author keywords

reinforcement learning

Scientific reference

A. Agostini and E. Celaya. A competitive strategy for function approximation in Q-learning, 22nd International Joint Conference on Artificial Intelligence, 2011, Barcelona, pp. 1146-1151.